CSE DSI Machine Learning Seminar with Robert Pinsler (Microsoft Research)

AI for Materials Discovery and Simulation

The design of functional materials with desired properties is essential in driving technological advances in areas like energy storage, catalysis, and carbon capture. AI for Materials Discovery and Simulation aims to significantly accelerate this process. In the first part of this talk, I will introduce MatterGen, a diffusion-based model that generates stable, diverse inorganic materials across the periodic table and can further be fine-tuned to steer the generation towards a broad range of property constraints. In the second part of this talk, I will present MatterSim, a deep learning model for efficient atomistic simulations at first-principles level and accurate prediction of broad material properties across the periodic table, spanning a wide range of temperature and pressure conditions.

Dr. Robert Pinsler is a Senior Researcher at Microsoft Research Cambridge (UK) with a focus on machine learning for materials discovery. He holds a PhD from the University of Cambridge, where he worked on active learning and sequential decision-making approaches, including Bayesian batch active learning and reinforcement learning for robotics and molecular design.

CSE DSI Machine Learning Seminar with Robert Pinsler (Microsoft Research)

AI for Materials Discovery and Simulation

Share